Summary reasoning traces from LLMs maintain task performance and increase trust and appeal relative to answer-only or full-trace conditions, but none of the formats improve users' metacognitive calibration on reasoning tasks.
Title resolution pending
2 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
2
Pith papers citing it
1
external citations · external index
fields
cs.HC 2years
2026 2representative citing papers
Generative AI should be reframed as an active creative medium where humans use the SOSS process of shaping, observing, stirring, and selecting to sustain creative quality through conversation instead of judging outputs.
citing papers explorer
-
Explaining Too Much? Understanding How Large Language Model Reasoning Traces Influence Performance and Metacognition
Summary reasoning traces from LLMs maintain task performance and increase trust and appeal relative to answer-only or full-trace conditions, but none of the formats improve users' metacognitive calibration on reasoning tasks.
-
Material for Thought: Generative AI as an Active Creative Medium
Generative AI should be reframed as an active creative medium where humans use the SOSS process of shaping, observing, stirring, and selecting to sustain creative quality through conversation instead of judging outputs.